Why the Census Bureau Adopted Differential Privacy for the 2020 Census of Population

WATCH Series - John Abowd - US Census - June 6 - Noon - Room 2030

June 6, 2018 12:00 PM  to 
June 6, 2018 1:00 PM
NSF Room 2030

Abstract:

In September 2017, the Census Bureau announced, at a meeting of its Scientific Advisory Committee, that the test products from the 2018 End-to-End Census Test would be protected using differential privacy. The 2018 E2E test is the prototype of the full 2020 Census production system. Hence, unless the differential privacy system used for the 2018 E2E test fails, the expectation is that the full set of publication products from the 2020 Census will be protected by differential privacy. Importantly, the Bureau also indicated that the engineers implementing the 2018 E2E Test system and the 2020 Census production system would not be allowed to choose the privacy-loss budget, or make other decisions related to the allocation of that budget to different components of the privacy protection system. The decisions regarding the privacy-loss budget will be made by the Data Stewardship Executive Policy Committee (DSEP). This design ensures that the senior executive staff, and not the system engineers, will select the point on the privacy-loss, publication accuracy frontier that balances the dual mandates to produce data that are suitable for their intended uses and protective of the confidentiality of the respondents’ information.

Speaker:

John M. Abowd is Associate Director for Research and Methodology and Chief Scientist at the United States Census Bureau and the Edmund Ezra Day Professor of Economics, Professor of Statistics and Information Science at Cornell University. At the Census Bureau, he leads a directorate of research centers, each devoted to domains of investigation important to the future of social and economic statistics. At Cornell, his primary appointment is in the Department of Economics in the ILR School. He is also Research Associate at the National Bureau of Economic Research (on leave while serving in the federal government), Research Affiliate at the Centre de Recherche en Economie et Statistique (CREST, Paris, France), Research Fellow at the Institute for Labor Economics (IZA, Bonn, Germany), and Research Fellow at IAB (Institut für Arbeitsmarkt-und Berufsforschung, Nürnberg, Germany). Abowd is the Director of the Labor Dynamics Institute at Cornell. He is the past President (2014-2015) and Fellow of the Society of Labor Economists. He is past Chair (2013) of the Business and Economic Statistics Section and Fellow of the American Statistical Association. He is an elected member of the International Statistical Institute. Abowd is also a fellow of the Econometric Society. He served as a Distinguished Senior Research Fellow at the United States Census Bureau (1998-2016). He served on the National Academies’ Committee on National Statistics (2010-2016). He currently serves on the American Economic Association’s Committee on Economic Statistics (2013-2018). He served as Director of the Cornell Institute for Social and Economic Research (CISER) from 1999 to 2007. Prof. Abowd has taught and done research at Cornell University since 1987, including seven years on the faculty of the Johnson Graduate School of Management. His current research and many activities of the LDI focus on the creation, dissemination, privacy protection, and use of linked, longitudinal data on employees and employers. In his earlier work at the Census Bureau he provided scientific leadership for the Longitudinal Employer-Household Dynamics Program, which produces research and public-use data integrating censuses, demographic surveys, economic surveys, and administrative data. The LEHD Program’s public use data products include the Quarterly Workforce Indicators, the most detailed time series data produced on the demographic characteristics of local American labor markets and OnTheMap, a user-driven mapping tool for studying work-related commuting patterns. His original and ongoing research on integrated labor market data is done in collaboration with the Institut National de la Statistique et des Etudes Economiques (INSEE), the French national statistical institute. Prof. Abowd’s other research interests include network models for integrated labor market data; statistical methods for confidentiality protection of micro-data; international comparisons of labor market outcomes; executive compensation with a focus on international comparisons; bargaining and other wage-setting institutions; and the econometric tools of labor market analysis. Prof. Abowd served on the faculty at Princeton University, the University of Chicago, and the Massachusetts Institute of Technology before moving to Cornell.

To view the webinar, please register at: http://www.tvworldwide.com/events/nsf/180606/

This event is part of Webinars/Webcasts.

Meeting Type
Lecture, Webcast

Contacts
Nina Amla, (703) 292-7991, email: namla@nsf.gov

NSF Related Organizations
Directorate for Computer and Information Science and Engineering